Systems and methods are provided for using automatic speech recognition to analyze a voice interaction and verify compliance of an agent reading a script to a client during the voice interaction. In one aspect of the invention, a method may include conducting the voice interaction between the agent and a client, wherein the agent follows the script via a plurality of panels. From there, the voice interaction is evaluated via the plurality of panels employing panel-by-panel playback with an automatic speech recognition component adapted to analyze the voice interaction. As such, it may be determined, via generating a score using confidence level thresholds of an automatic speech recognition component such that confidence level thresholds are assigned to each of the plurality of panels and evaluating the score against at least one of a static standard and a varying standard, whether the agent has adequately followed the script.
Legal claims defining the scope of protection. Each claim is shown in both the original legal language and a plain English translation.
1. A method, comprising: conducting at least one voice interaction by at least one agent, wherein the at least one agent follows at least one script via at least one of a plurality of panels; logging the at least one voice interaction; evaluating the at least one logged voice interaction via the at least one of the plurality of panels employing panel-by-panel playback with at least one automatic speech recognition component adapted to analyze the at least one voice interaction; generating a score using confidence level thresholds of the least one automatic speech recognition component such that confidence level thresholds are assigned to each of the plurality of panels; and determining whether the at least one agent has adequately followed the at least one script based on the generated score.
A method for monitoring call center agent script adherence: An agent engages in a voice interaction, guided by a script presented in multiple panels. The voice interaction is recorded and then analyzed panel-by-panel using automatic speech recognition (ASR). ASR assigns confidence scores to each panel's spoken content. A score is generated based on the confidence levels associated with each panel, determining if the agent followed the script adequately.
2. The method of claim 1 comprising evaluating the score against at least one of a static standard and a varying standard.
In the method for monitoring call center agent script adherence described above, the ASR-generated confidence score is compared against a defined standard to determine script compliance. This standard can be either a fixed value or a dynamic threshold that changes based on factors like script complexity or agent experience.
3. The method of claim 1 comprising determining whether the at least one agent has adequately followed the at least one script based on the evaluated at least one logged voice interaction.
In the method for monitoring call center agent script adherence described above, whether or not the agent has followed the script is determined by evaluating the logged voice interaction. The evaluation process involves analyzing the recorded audio and transcribed text from each panel of the script to assess the agent's adherence to the prescribed dialogue and instructions.
4. The method of claim 1 comprising assigning a time displacement timestamp to each of the plurality of panels as they are presented and viewed by the at least one agent during the voice interaction.
In the method for monitoring call center agent script adherence described above, each panel of the script is timestamped when it's displayed to the agent during the call. This timestamp records the time when the agent is expected to read the content of that particular panel, enabling synchronization between the agent's actions and the recorded voice interaction.
5. The method of claim 4 , wherein the at least one voice interaction is logged in a log record.
In the method for monitoring call center agent script adherence where timestamps are assigned to script panels, the voice interaction, along with other metadata, is stored as a log record. This log record provides a complete record of the call, facilitating analysis and compliance tracking.
6. The method of claim 5 comprising logging a time displacement, based on the time displacement timestamp, per panel as a portion of the log record.
In the method for monitoring call center agent script adherence where the voice interaction is logged, the time displacement (timestamp) for each panel is included in the log record. This creates a detailed timeline of panel presentations and allows for precise analysis of agent behavior at specific points during the call.
7. The method of claim 1 , wherein conducting at least one voice interaction includes conducting at least one voice interaction involving a telemarketing agent.
In the method for monitoring call center agent script adherence described above, the voice interaction involves a telemarketing agent. The system specifically addresses the need to monitor and ensure compliance with telemarketing scripts, where adherence to specific wording and disclosures is crucial.
8. The method of claim 1 , wherein conducting at least one voice interaction includes conducting at least one voice interaction governed by at least one script that includes text corresponding to at least one offer of at least one of goods and services.
In the method for monitoring call center agent script adherence described above, the script contains text related to offers for goods or services. This use case focuses on scenarios where agents are presenting specific products or services and the system ensures they accurately convey the required information.
9. The method of claim 1 , wherein conducting at least one voice interaction includes conducting the at least one voice interaction on at least one of a communications network, a publicly switched telephone network (PSTN), and the Internet.
In the method for monitoring call center agent script adherence described above, the voice interaction occurs over various communication networks, including standard telephone lines (PSTN), the internet, or other communication systems. The system is designed to function independently of the underlying network infrastructure.
10. The method of claim 1 , wherein evaluating the at least one logged voice interaction includes providing a script compliance module accessible via a user interface and a communications network, the communications network including at least one of an analog telephone, a digital telephone, an internet-based network, a wireless network, and a selected voice communications supporting network.
In the method for monitoring call center agent script adherence described above, a script compliance module is provided through a user interface accessible via a communication network (analog, digital, internet-based or wireless). This module provides the necessary tools to set up, monitor and evaluate agent script compliance.
11. The method of claim 10 , comprising converting the at least one voice interaction received via the communications network into at least one digital signal comprising at least one spectral representation of the at least one voice interaction.
In the script compliance method with a user interface accessible via a communication network as above, the voice interaction received is converted into a digital signal. The digital signal includes spectral representation of the voice interaction, enabling signal processing and analysis.
12. The method of claim 11 comprising comparing the at least one digital signal to at least one reference standard that includes at least one known vocabulary.
In the method where the voice interaction is converted to a digital signal as described above, the digital signal is compared to a reference standard containing a defined vocabulary. The comparison helps identify spoken words and phrases and determine their accuracy.
13. The method of claim 12 , wherein evaluating the at least one logged voice interaction includes matching the at least one digital signal to at least one of words and phrases contained in the at least one reference standard.
In the method where the voice interaction is compared to a reference standard as above, the digital signal is matched against words and phrases contained within the reference standard. This matching process identifies the spoken content and assess compliance with the script.
14. A system, comprising: a logging component adapted to log a time displacement of at least one voice interaction by at least one agent, wherein the at least one agent follows at least one script via at least one of a plurality of panels; and at least one automatic speech recognition component communicably coupled to the logging component, the at least one automatic speech recognition component adapted to analyze the at least one voice interaction using each of the plurality of panels and to determine whether the at least one agent has adequately followed the at least one script based on a score using confidence level thresholds assigned to each of the plurality of panels of the at least one automatic speech recognition component.
A system for monitoring call center agent script adherence: A logging component records the timing of voice interactions, capturing the sequence of panels displayed from a script presented to the agent. An Automatic Speech Recognition (ASR) component is linked to the logging unit and analyzes the voice interactions associated with each panel. The ASR uses assigned confidence thresholds for each panel to determine the agent’s adherence to the script.
15. The system of claim 14 , wherein the score is evaluated against at least one of a static standard and a varying standard.
In the system for monitoring call center agent script adherence described above, the ASR-generated confidence score is compared against a defined standard to determine script compliance. This standard can be either a fixed value or a dynamic threshold that changes based on factors like script complexity or agent experience.
16. The system of claim 14 , comprising an action component operable to cause at least one action to be taken.
The system for monitoring call center agent script adherence described above also includes an action component. This component can trigger actions based on the determined script compliance.
17. The system of 16 , wherein the at least one action is based upon a determination by the at least one automatic speech recognition component as to whether the at least one agent has adequately followed the at least one script.
In the system for monitoring call center agent script adherence that includes an action component as above, the action taken is based on whether the agent adequately followed the script, as determined by the automatic speech recognition component's analysis.
18. The system of claim 16 , wherein the at least one action is at least one signal transmitted to the at least one agent.
In the system for monitoring call center agent script adherence that includes an action component as above, the action taken is a signal transmitted to the agent. This signal can provide real-time feedback, coaching, or warnings related to script adherence during the call.
19. The system of claim 16 , wherein the at least one action is at least one signal transmitted to at least one reviewing authority.
In the system for monitoring call center agent script adherence that includes an action component as above, the action taken is a signal transmitted to a reviewing authority. This signal alerts supervisors or quality assurance personnel to calls where agents may not be following the script correctly.
20. The system of claim 16 , wherein the at least one action is an entry being made in a script compliance incentive system.
In the system for monitoring call center agent script adherence that includes an action component as above, the action taken is an entry made in a script compliance incentive system. This could be a point, reward, or other form of recognition for agents who consistently adhere to the script guidelines.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
December 5, 2012
August 6, 2013
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.